Title | ||
---|---|---|
A 2.5D semantic segmentation of the pancreas using attention guided dual context embedded U-Net |
Abstract | ||
---|---|---|
•Designed the light-weight 3D voxel by synthesizing adjacent three CT slices and proposed the corresponding label mapping method.•2.5D segmentation method was designed by applying 2D CNN to the segmentation of light-weight 3D voxels.•Based on U-Net, Multi-attention Dual Context Network (MADC-Net) was proposed for pancreatic segmentation of CT images, while attention mechanism and dual context feature fuse method were used to retain the meaningful features and aggregate global context features and local detailed features for pancreatic segmentation.•The proposed 2.5D segmentation method demonstrated improved and robust performance in segmentation of pancreas, suggesting the ability to provide consistent delineation and assist radiologists in their clinical applications. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1016/j.neucom.2022.01.044 | Neurocomputing |
Keywords | DocType | Volume |
Pancreatic segmentation,2.5D segmentation,Attention mechanism,Computed tomography,Convolutional neural network | Journal | 480 |
ISSN | Citations | PageRank |
0925-2312 | 0 | 0.34 |
References | Authors | |
0 | 8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jingyuan Li | 1 | 0 | 0.34 |
Guanqun Liao | 2 | 0 | 0.34 |
Wenfang Sun | 3 | 1 | 0.75 |
Ji Sun | 4 | 0 | 0.34 |
Tai Sheng | 5 | 0 | 0.34 |
Kaibin Zhu | 6 | 0 | 0.34 |
Karen M. von Deneen | 7 | 1 | 0.75 |
Yi Zhang | 8 | 0 | 0.34 |